Artificial Intelligence and Robotics Commons^™

Application Of Reinforcement Learning To Precision Aerial Delivery System Control In Adverse Wind Conditions, Radman Zarbock

The Journal of Purdue Undergraduate Research

Precision aerial delivery systems (PADS) are a subset of airdropped parachute-leveraging package delivery systems that use autonomous guidance, navigation, and control (GNC) to reach targets with high degrees of accuracy. This technology emerged in the 1990s, and strides have been made since to improve the reliability of traditional physics-based controllers that guide PADS. However, these algorithms still struggle to deliver acceptable performance results when PADS are subjected to austere operating environments, such as those with unpredictable wind. Building on a foundational study in 2022 that used artificial intelligence (AI) and machine learning to improve PADS GNC performance, this study aims …

A Deep Learning Framework With Explainable Ai For Atmospheric Blocking Detection And Interpretation, Devansh Khandelwal

Discovery Undergraduate Interdisciplinary Research Internship

Atmospheric blocking is a large-scale quasi-stationary phenomenon in mid-latitude circulation, characterized by persistent high-pressure systems that disrupt the typical west-to-east flow of the jet stream. These systems can cause extreme weather events—such as heatwaves, cold spells, or droughts—that persist for days or even weeks. This study proposes a deep learning framework to predict and interpret the occurrence of atmospheric blocking by integrating geophysical precursors such as geopotential height (Z500), stream function (SF200), and potential vorticity. These features, which are dynamically linked to blocking onset and persistence, serve as inputs to a Convolutional Neural Network model trained on the CESM Large …

Evaluating The Evaluation Matrices: Integrating Spatial Assessment In Geospatial Ai Model Training And Evaluation, Fangzheng Lyu

I-GUIDE Forum

This paper examines the limitations of current evaluation metrics in GeoAI. Through two case studies on deep learning models—a building detection classification problem and a remote sensing image fusion regression problem—this paper demonstrates how traditional statistical evaluation matrices alone can be misleading in geospatial problems. The findings indicate that traditional metrics (e.g., RMSE, MAE) used in current GeoAI models can have difficulty capturing the spatial dimensions inherent to geospatial problems. This paper suggests that the model evaluation process in GeoAI should move beyond traditional evaluation matrices by integrating spatial thinking throughout the modeling pipeline—not only incorporating spatial accuracy in model …

Selected Artificial Intelligence Provisions In U.S. Fiscal Year 2025 National Defense Authorization Act, Bert Chapman

Libraries Faculty and Staff Presentations

The 2025 Fiscal Year National Defense Authorization Act contains multiple provisions relating to artificial intelligence (AI). These congressionally mandated provisions direct various sections of the Department of Defense (DOD) and individual U.S. armed service branches to execute congressional intent for AI policymaking. Examples of such intent include identifying and planning DOD's AI workforce, demonstrating AI biotechnology applications for national security, improving the human usability of AI systems, and establishing an AI security center. This presentation will note that reports on these initiatives must be prepared for relevant congressional oversight committees, and, in many cases, are in many cases, publicly released …

Application Of Physics-Informed Neural Networks On Crop Yield Prediction At Multiple Scales, Aditya P. Prabhu, Pratishtha Poudel, James V. Krogmeier

Discovery Undergraduate Interdisciplinary Research Internship

Accurately predicting crop yields is a critical challenge in sustainable agriculture, food security, and farm management. Traditional process-based models rely on agronomic domain knowledge, crop physiology and statistical approaches, while purely data-driven approaches leverage machine learning or deep learning models using meteorological and spatial data. Unfortunately, these black-box models(Data-drive approaches) often lack interpretability and fail to incorporate well-established physical principles. This project explores a hybrid approach by implementing Physics Informed Neural Networks, mainly, physics-based recurrent neural networks (PI-RNNs) for time-series yield prediction. PINNs allow for the integration of scientific knowledge directly into the model by embedding physical laws as constraints …

Implication Of Generative Ai On Education And Research, Riddhi Gupta

The Journal of Purdue Undergraduate Research

No abstract provided.

Predictive Maintenance Analysis Of Turbofan Engine Sensor Data, Stanley A. Melkumian

The Journal of Purdue Undergraduate Research

Predictive maintenance in aviation and aerospace applications is among the most explored problems in machine learning (ML) and artificial intelligence (AI), and datasets such as NASA’s C-MAPPS turbofan engine degradation simulation data have proven invaluable, helping researchers explore numerous questions on engine performance, maintenance, and failure. The purpose of this study was to extend the current research on predicting the remaining useful life (RUL) of engines and their risk classification. Starting with simple yet under-investigated nonlinear survival and random forest models, the analysis implemented eXtreme Gradient Boosting (XGBoost) and long short-term memory (LSTM) from TensorFlow’s Keras library. For both regression …

Tradeoffs Of Generalization, Kyra M. Abrams, Peter T. Darch

I-GUIDE Forum

Models used in geospatial data science are often built and optimized for a specific local context, such as a particular location at a point in time. However, upon publication, these models may be generalized beyond this context, reused in research simulating or predicting other times and places. Without sufficient information or documentation, bias embedded in these models can in turn result in bias in the reuser’s research outputs. Drawing on a long-term qualitative case study of aging dams researchers and developers of models used by these researchers, we find significant documentation gaps. We combine a literature-based genealogy with interviews with …

Smart Airports: Artificial Intelligence–Enabled Internet Of Things Networks Using Blockchain Technology, Edwin Ongola

Journal of Aviation Technology and Engineering

This article provides a perspective on how an internet of heterogeneous self-service airport terminal systems can be used for data collection, which is stored on a private or consortium blockchain depending on the ownership or operations of an airport or both. Such a setup would help to increase efficiency, reduce costs, and improve traveler experience at airport terminals. Moreover, it would allow airports to gather data directly from passengers as opposed to waiting to receive the same data from airlines. Subsequently, this data, now on a blockchain system, becomes a data source for other applications such as machine learning. In …

Fusing Classic Motion Energy Models And Deep Learning For Coarse-To-Fine Moving Object Segmentation, Matthias Tangemann, Matthias Kümmerer, Matthias Bethge

MODVIS Workshop

Classic motion energy models are able to predict a wide range of physiological and behavioral aspects of motion perception in humans. Whether these models can be used as a basis for higher-level tasks, such as moving object segmentation, has however hardly been explored yet. Here, we present a model that combines a motion energy representation with recent computer vision approaches for figure-ground segmentation of naturalistic stimuli. We find that unlike established motion segmentation models but similar to humans, our model generalizes to random-dot stimuli when only trained on RGB videos.

Promises And Risks Of Applying Ai Medical Imaging To Early Detection Of Cancers, And Regulation For Ai Medical Imaging, Yiyao Zhang

The Journal of Purdue Undergraduate Research

No abstract provided.

Graph Transformer Network For Flood Forecasting With Heterogeneous Covariates, Jimeng Shi, Vitalii Stebliankin, Zhaonan Wang, Shaowen Wang, Giri Narasimhan

I-GUIDE Forum

Floods can be very destructive causing heavy damage to life, property, and livelihoods. Global climate change and the consequent sea-level rise have increased the occurrence of extreme weather events, resulting in elevated and frequent flood risk. Therefore, accurate and timely flood forecasting in coastal river systems is critical to facilitate good flood management. However, the computational tools currently used are either slow or inaccurate. In this paper, we propose a Flood prediction tool using Graph Transformer Network (FloodGTN) for river systems. More specifically, FloodGTN learns the spatio-temporal dependencies of water levels at different monitoring stations using Graph Neural Networks (GNNs) …

Curriculum Design Of Artificial Intelligence And Sustainability In Secondary School, Jinyi Cai, Mei-Po Kwan, Chunyu Hou, Dong Liu, Yeung Yam

I-GUIDE Forum

Artificial Intelligence is revolutionizing numerous sectors with its transformative power, while at the same time, there is an increasing sense of urgency to address sustainability challenges. Despite the significance of both areas, secondary school curriculums still lack comprehensive integration of AI and sustainability education. This paper presents a curriculum designed to bridge this gap. The curriculum integrates progressive objectives, computational thinking competencies and system thinking components across five modules—awareness, knowledge, interaction, empowerment and ethics—to cater to varying learner levels. System thinking components help students understand sustainability in a holistic manner. Computational thinking competencies aim to cultivate computational thinkers to guide …

Reducing Uncertainty In Sea-Level Rise Prediction: A Spatial-Variability-Aware Approach, Subhankar Ghosh, Shuai An, Arun Sharma, Jayant Gupta, Shashi Shekhar, Aneesh Subramanian

I-GUIDE Forum

Given multi-model ensemble climate projections, the goal is to accurately and reliably predict future sea-level rise while lowering the uncertainty. This problem is important because sea-level rise affects millions of people in coastal communities and beyond due to climate change's impacts on polar ice sheets and the ocean. This problem is challenging due to spatial variability and unknowns such as possible tipping points (e.g., collapse of Greenland or West Antarctic ice-shelf), climate feedback loops (e.g., clouds, permafrost thawing), future policy decisions, and human actions. Most existing climate modeling approaches use the same set of weights globally, during either regression or …

The Model 2.0 And Friends: An Interim Report, Garrison W. Cottrell, Martha Gahl, Shubham Kulkarni, Shashank Venkatramani, Yash Shah, Keyu Long, Xuzhe Zhi, Shivaank Agarwal, Cody Li, Jingyuan He, Thomas Fischer

MODVIS Workshop

Last year, I reported on preliminary results of an anatomically-inspired deep learning model of the visual system and its role in explaining the face inversion effect. This year, I will report on new results and some variations on network architectures that we have explored, mainly as a way to generate discussion and get feedback. This is by no means a polished, final presentation!

We look forward to the group’s suggestions for these projects.

Automated Delineation Of Visual Area Boundaries And Eccentricities By A Cnn Using Functional, Anatomical, And Diffusion-Weighted Mri Data, Noah C. Benson, Bogeng Song, Toshikazu Miyata, Hiromasa Takemura, Jonathan Winawer

MODVIS Workshop

Delineating visual field maps and iso-eccentricities from fMRI data is an important but time-consuming task for many neuroimaging studies on the human visual cortex because the traditional methods of doing so using retinotopic mapping experiments require substantial expertise as well as scanner, computer, and human time. Automated methods based on gray-matter anatomy or a combination of anatomy and functional mapping can reduce these requirements but are less accurate than experts. Convolutional Neural Networks (CNNs) are powerful tools for automated medical image segmentation. We hypothesize that CNNs can define visual area boundaries with high accuracy. We trained U-Net CNNs with ResNet18 …

How Object Segmentation And Perceptual Grouping Emerge In Noisy Variational Autoencoders, Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog

MODVIS Workshop

Many animals and humans can recognize and segment objects from their backgrounds. Whether object segmentation is necessary for object recognition has long been a topic of debate. Deep neural networks (DNNs) excel at object recognition, but not at segmentation tasks - this has led to the belief that object recognition and segmentation are separate mechanisms in visual processing. Here, however, we show evidence that in variational autoencoders (VAEs), segmentation and faithful representation of data can be interlinked. VAEs are encoder-decoder models that learn to represent independent generative factors of the data as a distribution in a very small bottleneck layer; …

A Dynamical Model Of Binding In Visual Cortex During Incremental Grouping And Search, Daniel Schmid, Daniel A. Braun, Heiko Neumann

MODVIS Workshop

Binding of visual information is crucial for several perceptual tasks. To incrementally group an object, elements in a space-feature neighborhood need to be bound together starting from an attended location (Roelfsema, TICS, 2005). To perform visual search, candidate locations and cued features must be evaluated conjunctively to retrieve a target (Treisman&Gormican, Psychol Rev, 1988). Despite different requirements on binding, both tasks are solved by the same neural substrate. In a model of perceptual decision-making, we give a mechanistic explanation for how this can be achieved. The architecture consists of a visual cortex module and a higher-order thalamic module. While the …

U-No: U-Shaped Neural Operators, Md Ashiqur Rahman, Zachary E Ross, Kamyar Azizzadenesheli

Department of Computer Science Faculty Publications

Neural operators generalize classical neural networks to maps between infinite-dimensional spaces, e.g., function spaces. Prior works on neural operators proposed a series of novel methods to learn such maps and demonstrated unprecedented success in learning solution operators of partial differential equations. Due to their close proximity to fully connected architectures, these models mainly suffer from high memory usage and are generally limited to shallow deep learning models. In this paper, we propose U-shaped Neural Operator (U-NO), a U-shaped memory enhanced architecture that allows for deeper neural operators. U-NOs exploit the problem structures in function predictions and demonstrate fast training, data …

Prerequisite Course Recommendation Based On Course Description And Students’ Grades, Haozhe Zhou

The Journal of Purdue Undergraduate Research

No abstract provided.

Estimating Vehicular Traffic Intensity With Deep Learning And Semantic Segmentation, Logan Bradley-Trietsch

The Journal of Purdue Undergraduate Research

No abstract provided.

Literature Review: How U.S. Government Documents Are Addressing The Increasing National Security Implications Of Artificial Intelligence, Bert Chapman

Libraries Faculty and Staff Scholarship and Research

This article emphasizes the increasing importance of artificial intelligence (AI) in military and national security policy making. It seeks to inform interested individuals about the proliferation of publicly accessible U.S. government and military literature on this multifaceted topic. An additional objective of this endeavor is encouraging greater public awareness of and participation in emerging public policy debate on AI's moral and national security implications..

Smiler: Consistent And Usable Saliency Model Implementations, Toni Kunic, Calden Wloka, John K. Tsotsos

MODVIS Workshop

The Saliency Model Implementation Library for Experimental Research (SMILER) is a new software package which provides an open, standardized, and extensible framework for maintaining and executing computational saliency models. This work drastically reduces the human effort required to apply saliency algorithms to new tasks and datasets, while also ensuring consistency and procedural correctness for results and conclusions produced by different parties. At its launch SMILER already includes twenty three saliency models (fourteen models based in MATLAB and nine supported through containerization), and the open design of SMILER encourages this number to grow with future contributions from the community. The project …

Is The Selective Tuning Model Of Visual Attention Still Relevant?, John K. Tsotsos

MODVIS Workshop

No abstract provided.

Deep Machine Learning For Mechanical Performance And Failure Prediction, Elijah Reber, Nickolas D. Winovich, Guang Lin

The Summer Undergraduate Research Fellowship (SURF) Symposium

Deep learning has provided opportunities for advancement in many fields. One such opportunity is being able to accurately predict real world events. Ensuring proper motor function and being able to predict energy output is a valuable asset for owners of wind turbines. In this paper, we look at how effective a deep neural network is at predicting the failure or energy output of a wind turbine. A data set was obtained that contained sensor data from 17 wind turbines over 13 months, measuring numerous variables, such as spindle speed and blade position and whether or not the wind turbine experienced …

Investigating Dataset Distinctiveness, Andrew Ulmer, Kent W. Gauen, Yung-Hsiang Lu, Zohar R. Kapach, Daniel P. Merrick

The Summer Undergraduate Research Fellowship (SURF) Symposium

Just as a human might struggle to interpret another human’s handwriting, a computer vision program might fail when asked to perform one task in two different domains. To be more specific, visualize a self-driving car as a human driver who had only ever driven on clear, sunny days, during daylight hours. This driver – the self-driving car – would inevitably face a significant challenge when asked to drive when it is violently raining or foggy during the night, putting the safety of its passengers in danger. An extensive understanding of the data we use to teach computer vision models – …

Deep Neural Network Architectures For Modulation Classification Using Principal Component Analysis, Sharan Ramjee, Shengtai Ju, Diyu Yang, Aly El Gamal

The Summer Undergraduate Research Fellowship (SURF) Symposium

In this work, we investigate the application of Principal Component Analysis to the task of wireless signal modulation recognition using deep neural network architectures. Sampling signals at the Nyquist rate, which is often very high, requires a large amount of energy and space to collect and store the samples. Moreover, the time taken to train neural networks for the task of modulation classification is large due to the large number of samples. These problems can be drastically reduced using Principal Component Analysis, which is a technique that allows us to reduce the dimensionality or number of features of the samples …

Applying Machine Learning To Computational Chemistry: Can We Predict Molecular Properties Faster Without Compromising Accuracy?, Hanjing Xu, Pradeep Gurunathan, Lyudmila Slipchenko

The Summer Undergraduate Research Fellowship (SURF) Symposium

Non-covalent interactions are crucial in analyzing protein folding and structure, function of DNA and RNA, structures of molecular crystals and aggregates, and many other processes in the fields of biology and chemistry. However, it is time and resource consuming to calculate such interactions using quantum-mechanical formulations. Our group has proposed previously that the effective fragment potential (EFP) method could serve as an efficient alternative to solve this problem. However, one of the computational bottlenecks of the EFP method is obtaining parameters for each molecule/fragment in the system, before the actual EFP simulations can be carried out. Here we present a …

Large-Scale Discovery Of Visual Features For Object Recognition, Drew Linsley, Sven Eberhardt, Dan Shiebler, Thomas Serre

MODVIS Workshop

A central goal in vision science is to identify features that are important for object and scene recognition. Reverse correlation methods have been used to uncover features important for recognizing faces and other stimuli with low intra-class variability. However, these methods are less successful when applied to natural scenes with variability in their appearance.

To rectify this, we developed Clicktionary, a web-based game for identifying features for recognizing real-world objects. Pairs of participants play together in different roles to identify objects: A “teacher” reveals image regions diagnostic of the object’s category while a “student” tries to recognize the object. Aggregating …

Nondestructive Testing And Structural Health Monitoring Based On Adams And Svm Techniques, Gang Jiang, Yi Ming Deng, Ji Tai Niu

The 8th International Conference on Physical and Numerical Simulation of Materials Processing

No abstract provided.